RSHallu: Dual-Mode Hallucination Evaluation for Remote-Sensing Multimodal Large Language Models with Domain-Tailored Mitigation
PELLI: Framework to effectively integrate LLMs for quality software generation
Beyond Confidence: The Rhythms of Reasoning in Generative Models
Flow caching for autoregressive video generation
Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval
Time Series Foundation Models for Energy Load Forecasting on Consumer Hardware: A Multi-Dimensional Zero-Shot Benchmark
ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-Seeking Agents
FedPS: Federated data Preprocessing via aggregated Statistics
Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis
The CLEF-2026 FinMMEval Lab: Multilingual and Multimodal Evaluation of Financial AI Systems
Interactive LLM-assisted Curriculum Learning for Multi-Task Evolutionary Policy Search
Resource-Efficient Model-Free Reinforcement Learning for Board Games
Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System
Traceable, Enforceable, and Compensable Participation: A Participation Ledger for People-Centered AI Governance
What do people want to fact-check?
Computational Phenomenology of Temporal Experience in Autism: Quantifying the Emotional and Narrative Characteristics of Lived Unpredictability
Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
Rotary Positional Embeddings as Phase Modulation: Theoretical Bounds on the RoPE Base for Long-Context Transformers
Healthy Harvests: A Comparative Look at Guava Disease Classification Using InceptionV3
FeatureBench: Benchmarking Agentic Coding for Complex Feature Development
RiemannGL: Riemannian Geometry Changes Graph Deep Learning
LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules
Fine-Tuning GPT-5 for GPU Kernel Generation
Enhancing Predictability of Multi-Tenant DNN Inference for Autonomous Vehicles' Perception
ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
CVPL: A Geometric Framework for Post-Hoc Linkage Risk Assessment in Protected Tabular Data
From Buffers to Registers: Unlocking Fine-Grained FlashAttention with Hybrid-Bonded 3D NPU Co-Design
OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories
ContactGaussian-WM: Learning Physics-Grounded World Model from Videos
Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting
Linguistic Indicators of Early Cognitive Decline in the DementiaBank Pitt Corpus: A Statistical and Machine Learning Study
Language Model Inversion through End-to-End Differentiation
GraphSeek: Next-Generation Graph Analytics with LLMs
Conversational Behavior Modeling Foundation Model With Multi-Level Perception
Chatting with Images for Introspective Visual Thinking
Interpretable Attention-Based Multi-Agent PPO for Latency Spike Resolution in 6G RAN Slicing
In-the-Wild Model Organisms: Mitigating Undesirable Emergent Behaviors in Production LLM Post-Training via Data Attribution
SteuerLLM: Local specialized large language model for German tax law analysis
GRASP: group-Shapley feature selection for patients
General Flexible $f$-divergence for Challenging Offline RL Datasets with Low Stochasticity and Diverse Behavior Policies
DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning
Direct Learning of Calibration-Aware Uncertainty for Neural PDE Surrogates
Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
Learning to Compose for Cross-domain Agentic Workflow Generation
Weight Decay Improves Language Model Plasticity
Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows
GENIUS: Generative Fluid Intelligence Evaluation Suite
Beyond VLM-Based Rewards: Diffusion-Native Latent Reward Modeling
Implicit Probabilistic Reasoning Does Not Reflect Explicit Answers in Large Language Models
Metareasoning in uncertain environments: a meta-BAMDP framework